Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Defect textures.
Статті в журналах з теми "Defect textures"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Defect textures".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Zhou, Lei, Bingya Ma, Yanyan Dong, Zhewen Yin, and Fan Lu. "DCFE-YOLO: A novel fabric defect detection method." PLOS ONE 20, no. 1 (January 14, 2025): e0314525. https://doi.org/10.1371/journal.pone.0314525.
Повний текст джерелаАнотація:
Accurate detection of fabric defects is crucial for quality control in the textile industry. However, the task of fabric defect detection remains highly challenging due to the complex textures and diverse defect patterns. To address the issues of inaccurate localization and false positives caused by complex textures and varying defect sizes, this paper proposes an improved YOLOv8-based fabric defect detection method. First, Dynamic Snake Convolution is introduced into the backbone network to enhance sensitivity to elongated and subtle defects, improving the extraction of edge and texture details. Second, a Channel Priority Convolutional Attention mechanism is incorporated after the Spatial Pyramid Pooling layer to enable more precise defect localization by leveraging multi-scale structures and channel priors. Finally, the feature fusion network integrates Partial Convolution and Efficient Multi-scale Attention, optimizing the fusion of information across different feature levels and spatial scales, which enhances the richness and accuracy of feature representations while reducing computational complexity. Experimental results demonstrate a significant improvement in detection performance. Specifically, mAP@0.5 increased by 2.9%, precision improved by 3.5%, and mAP@0.5:0.95 rose by 2.3%, highlighting the model’s superior capability in detecting complex defects. The project is available at https://github.com/lilian998/fabric.
2
Carrilho, Rui, Kailash A. Hambarde, and Hugo Proença. "A Novel Dataset for Fabric Defect Detection: Bridging Gaps in Anomaly Detection." Applied Sciences 14, no. 12 (June 19, 2024): 5298. http://dx.doi.org/10.3390/app14125298.
Повний текст джерелаАнотація:
Detecting anomalies in texture has become a significant concern across various industrial processes. One prevalent application of this is in inspecting patterned textures, especially in the domain of fabric defect detection, which is a commonly encountered scenario. This task entails dealing with a wide array of colours and textile varieties, spanning a broad spectrum of fabrics. Due to the extensive diversity in colours, textures, and defect characteristics, fabric defect detection presents a complex and formidable challenge within the realm of patterned texture inspection. While recent trends have seen a rise in the utilization of deep learning methods for anomaly detection, there still exist notable gaps in this field. In this paper, we introduce a novel dataset comprising a diverse selection of fabrics and defects from a textile company based in Portugal. Our contributions encompass the provision of this unique dataset and the evaluation of state-of-the-art (SOTA) methods’ performance on our dataset.
3
Zhang, Yuming, Zhongyuan Gao, Chao Zhi, Mengqi Chen, Youyong Zhou, Shuai Wang, Sida Fu, and Lingjie Yu. "A novel defect generation model based on two-stage GAN." e-Polymers 22, no. 1 (January 1, 2022): 793–802. http://dx.doi.org/10.1515/epoly-2022-0071.
Повний текст джерелаАнотація:
Abstract The fabric defect models based on deep learning often demand numerous training samples to achieve high accuracy. However, obtaining a complete dataset containing all possible fabric textures and defects is a big challenge due to the sophisticated and various fabric textures and defect forms. This study created a two-stage deep pix2pixGAN network called Dual Deep pix2pixGAN Network (DPGAN) to address the above problem. The defect generation model was trained based on the DPGAN network to automatically “transfer” defects from defected fabric images to clean, defect-free fabric images, thus strengthening the training data. To evaluate the effectiveness of the defect generation model, extensive comparative experiments were conducted to assess the performance of the fabric defect detection before and after data enhancement. The results indicate that the detection accuracy was improved regarding the belt_yarn, hole, and stain defect.
4
Shi, Hui, Gangyan Li, and Hanwei Bao. "Lightweight Reconstruction Network for Surface Defect Detection Based on Texture Complexity Analysis." Electronics 12, no. 17 (August 27, 2023): 3617. http://dx.doi.org/10.3390/electronics12173617.
Повний текст джерелаАнотація:
Deep learning networks have shown excellent performance in surface defect recognition and classification of certain industrial products. However, most industrial product defect samples are scarce and have a wide variety of defect types, making methods that require a large number of defect samples for training unsuitable. In this paper, a lightweight surface defect detection network (LRN-L) based on texture complexity analysis is proposed. Only a large number of defect-free samples, which can be easily obtained, are needed to detect defects. LRN-L includes two stages: texture reconstruction stage and defect localization stage. In the texture reconstruction phase, a lightweight reconstruction network (LRN) based on convolutional autoencoder is designed, which can reconstruct defect-free texture images; a loss function combining structural loss and L1 loss is proposed to improve the detection effect; we built a calculation model for image complexity, calculated the texture complexity for texture samples, and divided textures into three levels based on complexity. In the defect localization stage, the residual between the reconstructed image and the original image is taken as the possible region of the defect, and the defect localization is realized via a segmentation algorithm. In this paper, the network structure, loss function, texture complexity and other factors of LRN-L are analyzed in detail and compared with other similar algorithms on multiple texture datasets. The results show that LRN-L has strong robustness, accuracy and generalization ability, and is more suitable for industrial online detection.
5
Li, Feng, Lina Yuan, Kun Zhang, and Wenqing Li. "A defect detection method for unpatterned fabric based on multidirectional binary patterns and the gray-level co-occurrence matrix." Textile Research Journal 90, no. 7-8 (October 1, 2019): 776–96. http://dx.doi.org/10.1177/0040517519879904.
Повний текст джерелаАнотація:
A new texture-feature description operator, called the multidirectional binary patterns (MDBP) operator, is proposed in this paper. The operator can extract the detailed distribution of textures in local regions by comparing the differences in the gray levels between neighboring pixels. Moreover, the texture expression ability is enhanced by focusing on the texture features in the linear neighborhood of the image in multiple directions. The MDBP operator was modified by introducing a “uniform” pattern to reduce the grayscale values in the image. Combining the “uniform” MDBP operator and the gray-level co-occurrence matrix, an unpatterned fabric-defect detection scheme is proposed, including texture-feature extraction and detection stages. In the first stage, the multidirectional texture-feature matrix of a nondefective fabric image is extracted, and then the detection threshold is determined based on the similarity between the feature matrices. In the second stage, the defect is detected with the detection threshold. The proposed method is adapted to various grayscale textile images with different characteristics and is robust to a wide variety of image-processing operations. In addition, it is invariant to grayscale changes, performs well when representing textures and detecting defects and has lower computational complexity than other methods.
6
Mo, Dongmei, and Wai Keung Wong. "Fabric Defect Classification based on Deep Hashing Learning." AATCC Journal of Research 8, no. 1_suppl (September 2021): 191–201. http://dx.doi.org/10.14504/ajr.8.s1.23.
Повний текст джерелаАнотація:
Classifying categories of fabric defects can greatly help to identify the source of causing fabric defects in the textile manufacturing process. Most existing artificial intelligence based methods focus on identifying and locating defective regions and do not analyze the categories of the defects. On the other hand, as current fabric defect detection methods depend on handcrafted features, they can only handle fabric with specific patterns or textures. In this paper, we propose a novel model which can learn high-level representation from the automatic observations of the input images that can recognize the categories of the defects for various fabric patterns and textures, instead of only locating defects on specific patterns. Experimental results show that the proposed method is superior to the state-of-the-art deep hash methods in terms of fabric defect classification.
7
Li, Jianqi, Binfang Cao, Fangyan Nie, and Minhan Zhu. "Feature Extraction of Foam Nickel Surface Based on Multi-Scale Texture Analysis." Journal of Advanced Computational Intelligence and Intelligent Informatics 23, no. 2 (March 20, 2019): 175–82. http://dx.doi.org/10.20965/jaciii.2019.p0175.
Повний текст джерелаАнотація:
In the foam nickel process, texture is the indicator of foam nickel performance. In order to recognize foam nickel surface defects accurately and provide guidance for production operations, this paper proposes a method for extracting foam nickel image textures based on multi-scale texture analysis. First, nonsubsampled contourlet (NSCT) is used to carry out foam nickel image multi-scale decomposition, and the low-frequency and high-frequency components following decomposition are used to characterize different defect details. Then, the Haralick eigenvalue, which measures the foam nickel image texture information at each sub-band, is calculated. The KPCA and optimal DAG-SVM are adopted in order to reduce the parameter dimension and clarify defects. Tests are carried out on the foam nickel surface image samples, including crack, scratch, pollution, leakage, and indentation tests. The results indicate that the method proposed in this paper can extract different pieces of detailed texture information and can achieve a defect-identifying accuracy of up to 88.9%.
8
Liu, Yang, and Weiqi Yuan. "A Distributed System-Based Multiplex Networks to Extract Texture Feature." International Journal of Distributed Systems and Technologies 13, no. 3 (July 1, 2022): 1–11. http://dx.doi.org/10.4018/ijdst.307991.
Повний текст джерелаАнотація:
Defect detection is an indispensable part of quality detection in manufacturing. It is a challenging task to recognize defects on the surface of castings with random textures. This paper proposes a texture extraction method based on multiplex networks for defect segmentation in a random background. The proposed method redefines the image information in the form of multiplex network topologies according to the different properties of casting surface texture. Finally, the proposed method segments different texture regions by extracting the similarity of texture primitives in the multiplex networks. The study conducted experiments in a distributed system environment, and the results show that the proposed method is effective in actual industrial data sets. As an interdisciplinary application of network science and machine vision, the proposed method provides a valuable application mode for the development of complex networks in new fields and provides a new research idea for the texture analysis of castings.
9
Zhang, Huanhuan, Jinxiu Ma, Junfeng Jing, and Pengfei Li. "Fabric Defect Detection Using L0 Gradient Minimization and Fuzzy C-Means." Applied Sciences 9, no. 17 (August 26, 2019): 3506. http://dx.doi.org/10.3390/app9173506.
Повний текст джерелаАнотація:
In this paper, we present a robust and reliable framework based on L0 gradient minimization (LGM) and the fuzzy c-means (FCM) method to detect various fabric defects with diverse textures. In our framework, the L0 gradient minimization is applied to process the fabric images to eliminate the influence of background texture and preserve sharpened significant edges on fabric defects. Then, the processed fabric images are clustered by using the fuzzy c-means. Through continuous iterative calculation, the clustering centers of fabric defects and non-defects are updated to realize the defect regions segmentation. We evaluate the proposed method on various samples, which include plain fabric, twill fabric, star-patterned fabric, dot-patterned fabric, box-patterned fabric, striped fabric and statistical-texture fabric with different defect types and shapes. Experimental results demonstrate that the proposed method has a good detection performance compared with other state-of-the-art methods in terms of both subjective and objective tests. In addition, the proposed method is applicable to industrial machine vision detection with limited computational resources.
10
Song, K. Y., J. Kittler, and M. Petrou. "Defect detection in random colour textures." Image and Vision Computing 14, no. 9 (October 1996): 667–83. http://dx.doi.org/10.1016/0262-8856(96)84491-x.
Повний текст джерела
11
Hu, Guanghua, Junfeng Huang, Qinghui Wang, Jingrong Li, Zhijia Xu, and Xingbiao Huang. "Unsupervised fabric defect detection based on a deep convolutional generative adversarial network." Textile Research Journal 90, no. 3-4 (July 17, 2019): 247–70. http://dx.doi.org/10.1177/0040517519862880.
Повний текст джерелаАнотація:
Detecting and locating surface defects in textured materials is a crucial but challenging problem due to factors such as texture variations and lack of adequate defective samples prior to testing. In this paper we present a novel unsupervised method for automatically detecting defects in fabrics based on a deep convolutional generative adversarial network (DCGAN). The proposed method extends the standard DCGAN, which consists of a discriminator and a generator, by introducing a new encoder component. With the assistance of this encoder, our model can reconstruct a given query image such that no defects but only normal textures will be preserved in the reconstruction. Therefore, when subtracting the reconstruction from the original image, a residual map can be created to highlight potential defective regions. Besides, our model generates a likelihood map for the image under inspection where each pixel value indicates the probability of occurrence of defects at that location. The residual map and the likelihood map are then synthesized together to form an enhanced fusion map. Typically, the fusion map exhibits uniform gray levels over defect-free regions but distinct deviations over defective areas, which can be further thresholded to produce a binarized segmentation result. Our model can be unsupervisedly trained by feeding with a set of small-sized image patches picked from a few defect-free examples. The training is divided into several successively performed stages, each under an individual training strategy. The performance of the proposed method has been extensively evaluated by a variety of real fabric samples. The experimental results in comparison with other methods demonstrate its effectiveness in fabric defect detection.
12
Deepali Ujalambkar. "Industrial Product Surface Defect Detection Using CNN: A Deep Learning Approach." Panamerican Mathematical Journal 34, no. 3 (October 1, 2024): 84–95. http://dx.doi.org/10.52783/pmj.v34.i3.1775.
Повний текст джерелаАнотація:
Defect identification on surfaces of industrial products is a thought-provoking issue that has garnered significant attention. Defect identification of industrial products plays a primordial role in ensuring quality and reliability of products at all levels of the manufacturing process. The traditional approach relies fundamentally on the human inspection, which was unreliable and inefficient. Moreover, human inspection cannot meet the high standards for real-time detection required in industrial production situations. While methods used in image processing can solve difficult modules, they are not meant to deal with complicated ambient textures, noise, or lighting fluctuations. Innovative techniques have so been used by researchers and practitioners to improve and expedite the defect diagnosis process. This study classifies the product as "defect or not defect." and provides an intelligent approach for surface defect identification using convolutional neural network (CNN). The model demonstrates strong performance in identifying many types of industrial product defects, such as "crack, patch, inclusion, rolled, pitting, and scratching," by utilizing deep learning approaches. This involved training the model with several datasets featuring surface textures. The results were indicative of better performance, where the proposed method achieved outstanding precision in fault detection.
13
Si, Xiao Shu, Hong Zheng, and Xue Min Hu. "Fabric Defect Detection Based on SRG-PCNN." Advanced Materials Research 148-149 (October 2010): 1319–26. http://dx.doi.org/10.4028/www.scientific.net/amr.148-149.1319.
Повний текст джерелаАнотація:
Defect segmentation has been a focal point in fabric inspection research, and it remains challenging because it detects delicate features of defects complicated by variations in weave textures and changes in environmental factors. According to the different features between the normal fabric image and defect image, this paper presents an adaptive image segmentation method based on a simplified region growing pulse coupled neural network (SRG-PCNN) for detecting fabric defects. The validation tests on the developed algorithms were performed with fabric images, and results showed that SRG-PCNN is a feasible and efficient method for defect detection.
14
Zhang, Bo, and Chunming Tang. "A Method for Defect Detection of Yarn-Dyed Fabric Based on Frequency Domain Filtering and Similarity Measurement." Autex Research Journal 19, no. 3 (September 1, 2019): 257–62. http://dx.doi.org/10.1515/aut-2018-0040.
Повний текст джерелаАнотація:
Abstract The detection of defects in yarn-dyed fabric is one of the most difficult problems among the present fabric defect detection methods. The difficulty lies in how to properly separate patterns, textures, and defects in the yarn-dyed fabric. In this paper, a novel automatic detection algorithm is presented based on frequency domain filtering and similarity measurement. First, the separation of the pattern and yarn texture structure of the fabric is achieved by frequency domain filtering technology. Subsequently, segmentation of the periodic units of the pattern is achieved by using distance matching function to measure the fabric pattern. Finally, based on the similarity measurement technology, the pattern’s periodic unit is classified, and thus, automatic detection of the defects in the yarn-dyed fabric is accomplished.
15
Machon, Thomas, and Gareth P. Alexander. "Global defect topology in nematic liquid crystals." Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 472, no. 2191 (July 2016): 20160265. http://dx.doi.org/10.1098/rspa.2016.0265.
Повний текст джерелаАнотація:
We give the global homotopy classification of nematic textures for a general domain with weak anchoring boundary conditions and arbitrary defect set in terms of twisted cohomology, and give an explicit computation for the case of knotted and linked defects in R 3 , showing that the distinct homotopy classes have a 1–1 correspondence with the first homology group of the branched double cover, branched over the disclination loops. We show further that the subset of those classes corresponding to elements of order 2 in this group has representatives that are planar and characterize the obstruction for other classes in terms of merons. The planar textures are a feature of the global defect topology that is not reflected in any local characterization. Finally, we describe how the global classification relates to recent experiments on nematic droplets and how elements of order 4 relate to the presence of τ lines in cholesterics.
16
Cowling, Stephen James, Edward James Davis, Richard John Mandle, and John William Goodby. "ChemInform Abstract: Defect Textures of Liquid Crystals." ChemInform 45, no. 32 (July 24, 2014): no. http://dx.doi.org/10.1002/chin.201432267.
Повний текст джерела
17
OUYANG, Zhou, Huailiang ZHANG, Ziyang TANG, Ling PENG, and Sheng YU. "Research on defect detection algorithm of complex texture ceramic tiles based on visual attention mechanism." Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University 40, no. 2 (April 2022): 414–21. http://dx.doi.org/10.1051/jnwpu/20224020414.
Повний текст джерелаАнотація:
Aiming at the difficulty of detecting the surface defects of complex texture tiles, a salient target detection method based on the human visual attention mechanism is proposed and used for the detection of tile surface defects. Firstly, the image of ceramic tile surface is pretreated using the single-scale SSR light correction method and bilateral filtering method; Secondly, according to the principle of contrast and high-frequency suppression in the visual attention mechanism, aiming at the "imaging" and "aggregation" characteristics of complex background textures, a detection model based on the visual attention mechanism is established to determine and mark defects.According to the contrast principle and high-frequency suppression principle in visual attention mechanism, feature extraction of ceramic tile surface is carried out. Then, the image color patch weight salient map and image feature fused salient map are obtained, and the two maps are fused according to the image saliency criteria.Finally, the marked ceramic tile defects are determined and marked.Finally the marked ceramic tile defects are obtained. This defect detection algorithm and the other two algorithms are applied to three kinds of randomly selected complex texture ceramic tiles. The experimental results show that compared with other algorithms, our algorithm can achieve a comprehensive detection rate of more than 96% for complex texture ceramic tiles, and can obtain a good effect of ceramic tile defect detection as well.
18
Zhou, Jian, and Jianli Liu. "Segmentation of defects in textile fabric with robust texture representation and total variation." International Journal of Clothing Science and Technology 32, no. 6 (April 28, 2020): 813–23. http://dx.doi.org/10.1108/ijcst-10-2019-0157.
Повний текст джерелаАнотація:
PurposeVisual quality control on raw textile fabrics is a vital process in weaving factories to ensure their exterior quality (visual defects or imperfection) satisfying customer requirements. Commonly, this critical process is manually conducted by human inspectors, which can hardly provide a fast and reliable inspection results due to fatigue and subjective errors. To meet modern production needs, it is highly demanded to develop an automated defect inspection system by replacing human eyes with computer vision.Design/methodology/approachAs a structural texture, fabric textures can be effectively represented by a linearly summation of basic elements (dictionary). To create a robust representation of a fabric texture in an unsupervised manner, a smooth constraint is imposed on dictionary learning model. Such representation is robust to defects when using it to recover a defective image. Thus an abnormal map (likelihood of defective regions) can be computed by measuring similarity between recovered version and itself. Finally, the total variation (TV) based model is built to segment defects on the abnormal map.FindingsDifferent from traditional dictionary learning method, a smooth constraint is introduced in dictionary learning that not only able to create a robust representation for fabric textures but also avoid the selection of dictionary size. In addition, a TV based model is designed according to defects' characteristics. The experimental results demonstrate that (1) the dictionary with smooth constraint can generate a more robust representation of fabric textures compared to traditional dictionary; (2) the TV based model can achieve a robust and good segmentation result.Originality/valueThe major originality of the proposed method are: (1) Dictionary size can be set as a constant instead of selecting it empirically; (2) The total variation based model is built, which can enhance less salient defects, improving segmentation performance significantly.
19
MARIN, Florin Bogdan, and Mihaela MARIN. "Supervised Learning Plastic Defect Algorithm Detection." Annals of “Dunarea de Jos” University of Galati. Fascicle IX, Metallurgy and Materials Science 46, no. 4 (December 15, 2023): 89–92. http://dx.doi.org/10.35219/mms.2023.4.15.
Повний текст джерелаАнотація:
The goal of this research is to develop a supervised learning algorithm able to detect the defects of plastic’s material. Finding patterns or examples in a dataset that differ from the norm is known as anomaly detection in plastic textures. Anomalies, in the context of plastic textures, can refer to imperfections’ deviations, or anomalies in the material that may have an impact on the final product's overall quality. Conventional anomaly detection techniques frequently rely on rule-based systems or manual examination, which can be laborious, subjective, and unable to identify small anomalies.
20
Yu, Ronghao, Yun Liu, Rui Yang, and Yingna Wu. "VQGNet: An Unsupervised Defect Detection Approach for Complex Textured Steel Surfaces." Sensors 24, no. 19 (September 27, 2024): 6252. http://dx.doi.org/10.3390/s24196252.
Повний текст джерелаАнотація:
Defect detection on steel surfaces with complex textures is a critical and challenging task in the industry. The limited number of defect samples and the complexity of the annotation process pose significant challenges. Moreover, performing defect segmentation based on accurate identification further increases the task’s difficulty. To address this issue, we propose VQGNet, an unsupervised algorithm that can precisely recognize and segment defects simultaneously. A feature fusion method based on aggregated attention and a classification-aided module is proposed to segment defects by integrating different features in the original images and the anomaly maps, which direct the attention to the anomalous information instead of the irregular complex texture. The anomaly maps are generated more confidently using strategies for multi-scale feature fusion and neighbor feature aggregation. Moreover, an anomaly generation method suitable for grayscale images is introduced to facilitate the model’s learning on the anomalous samples. The refined anomaly maps and fused features are both input into the classification-aided module for the final classification and segmentation. VQGNet achieves state-of-the-art (SOTA) performance on the industrial steel dataset, with an I-AUROC of 99.6%, I-F1 of 98.8%, P-AUROC of 97.0%, and P-F1 of 80.3%. Additionally, ViT-Query demonstrates robust generalization capabilities in generating anomaly maps based on the Kolektor Surface-Defect Dataset 2.
21
Liu, Zhoufeng, Baorui Wang, Chunlei Li, Miao Yu, and Shumin Ding. "Fabric defect detection based on deep-feature and low-rank decomposition." Journal of Engineered Fibers and Fabrics 15 (January 2020): 155892502090302. http://dx.doi.org/10.1177/1558925020903026.
Повний текст джерелаАнотація:
Fabric defect detection plays an important role in controlling the quality of textile production. In this article, a novel fabric defect detection algorithm is proposed based on a multi-scale convolutional neural network and low-rank decomposition model. First, multi-scale convolutional neural network, which can extract the multi-scale deep feature of the image using multiple nonlinear transformations, is adopted to improve the characterization ability of fabric images with complex textures. The effective feature extraction makes the background lie in a low-rank subspace, and a sparse defect deviates from the low-rank subspace. Then, the low-rank decomposition model is constructed to decompose the feature matrix into the low-rank part (background) and the sparse part (salient defect). Finally, the saliency maps generated by the sparse matrix are segmented based on an improved optimal threshold to locate the fabric defect regions. Experimental results indicate that the feature extracted by the multi-scale convolutional neural network is more suitable for characterizing the fabric texture than the traditional hand-crafted feature extraction methods, such as histogram of oriented gradient, local binary pattern, and Gabor. The adopted low-rank decomposition model can effectively separate the defects from the background. Moreover, the proposed method is superior to state-of-the-art methods in terms of its adaptability and detection efficiency.
22
Zhong, Zhiyan, Hongxin Wang, and Dan Xiang. "Small Defect Detection Based on Local Structure Similarity for Magnetic Tile Surface." Electronics 12, no. 1 (December 30, 2022): 185. http://dx.doi.org/10.3390/electronics12010185.
Повний текст джерелаАнотація:
Surface defect detection is critical in manufacturing magnetic tiles to improve production yield. However, existing detection methods are difficult to use to accurately locate and segment small defects on magnetic tile images, because these defects always occupy extremely low proportions of images, and their visual features are difficult to identify, which means their feature representation for defect detection is quite weak. To address this issue, we propose an effective and feasible detection algorithm for small defects on magnetic tile surfaces. Firstly, based on local structure similarity of magnetic tile surfaces, the image is decomposed into low-rank and sparse matrices for estimating possible defect regions. To accurately locate defect areas while filtering out stains, textures, and noises, the sparse matrix is binarized and used for connected components analysis. Then, pixel values in the defect area are normalized, and the Retinex theory is applied to enhance the contrast between defects and background. Finally, an optimal threshold is determined by an automatic threshold segmentation method to segment the defect areas and edges precisely. Experimental results on a number of magnetic tile samples containing different types of defects demonstrated that the proposed algorithm outperforms the existing methods in terms of all evaluation metrics, showing broad industrial application prospects.
23
Mehta, Devang, and Noah Klarmann. "Autoencoder-Based Visual Anomaly Localization for Manufacturing Quality Control." Machine Learning and Knowledge Extraction 6, no. 1 (December 21, 2023): 1–17. http://dx.doi.org/10.3390/make6010001.
Повний текст джерелаАнотація:
Manufacturing industries require the efficient and voluminous production of high-quality finished goods. In the context of Industry 4.0, visual anomaly detection poses an optimistic solution for automatically controlled product quality with high precision. In general, automation based on computer vision is a promising solution to prevent bottlenecks at the product quality checkpoint. We considered recent advancements in machine learning to improve visual defect localization, but challenges persist in obtaining a balanced feature set and database of the wide variety of defects occurring in the production line. Hence, this paper proposes a defect localizing autoencoder with unsupervised class selection by clustering with k-means the features extracted from a pretrained VGG16 network. Moreover, the selected classes of defects are augmented with natural wild textures to simulate artificial defects. The study demonstrates the effectiveness of the defect localizing autoencoder with unsupervised class selection for improving defect detection in manufacturing industries. The proposed methodology shows promising results with precise and accurate localization of quality defects on melamine-faced boards for the furniture industry. Incorporating artificial defects into the training data shows significant potential for practical implementation in real-world quality control scenarios.
24
THATCHER, M. J., and M. J. MORGAN. "BIREFRINGENT ELECTROWEAK DEFECTS." International Journal of Modern Physics A 17, no. 14 (June 10, 2002): 1953–64. http://dx.doi.org/10.1142/s0217751x02010583.
Повний текст джерелаАнотація:
In this paper we examine the propagation of electromagnetic waves through electroweak textures and W-strings. The photon is associated with a negative mass squared term as a consequence of its coupling to the intermediate vector bosons from which the electroweak defect is constructed. The photon pseudo-mass depends on the polarization of the photon and results in electroweak defects exhibiting birefringent properties. We calculate the effective refractive index and birefringence length scale. The cosmological implications of birefringent electroweak defects are discussed.
25
Kim, Minsu, Hoon Jo, Moonsoo Ra, and Whoi-Yul Kim. "Weakly-Supervised Defect Segmentation on Periodic Textures Using CycleGAN." IEEE Access 8 (2020): 176202–16. http://dx.doi.org/10.1109/access.2020.3024554.
Повний текст джерела
26
Asha, V., N. U. Bhajantri, and P. Nagabhushan. "Similarity measures for automatic defect detection on patterned textures." International Journal of Information and Communication Technology 4, no. 2/3/4 (2012): 118. http://dx.doi.org/10.1504/ijict.2012.048758.
Повний текст джерела
27
Stanosz, Glen R., and Gary Laudermilch. "Variation in Frequency of Sugar Maple Bole Damage From Tree-Marking Materials." Northern Journal of Applied Forestry 9, no. 4 (December 1, 1992): 136–37. http://dx.doi.org/10.1093/njaf/9.4.136.
Повний текст джерелаАнотація:
Abstract Six blue tree-marking materials, commonly used to mark residual trees and those along boundaries, were evaluated for their potential to damage sugar maple boles. Materials were applied as 3-in. diameter spots in both spring and fall to trees of two bark textures in stands at four different locations. Damage was evaluated three growing seasons later. Cracks were the most frequent form of defect, but swelling, callus, and open cankers also occurred. Damage was observed in 192 of 1056 spots, and there was wide variation in the frequency of damage caused by different materials. There also were relationships between frequency of damage and both stand location and bark texture. Defects may be avoided by minimizing application to valuable trees and by using those marking materials which less frequently cause damage. North. J. Appl. For. 9(4):136-137.
28
ZHU, Runhu, Binjie XIN, Na DENG, and Mingzhu FAN. "Semantic Segmentation Using DeepLabv3+ Model for Fabric Defect Detection." Wuhan University Journal of Natural Sciences 27, no. 6 (December 2022): 539–49. http://dx.doi.org/10.1051/wujns/2022276539.
Повний текст джерелаАнотація:
Currently, numerous automatic fabric defect detection algorithms have been proposed. Traditional machine vision algorithms that set separate parameters for different textures and defects rely on the manual design of corresponding features to complete the detection. To overcome the limitations of traditional algorithms, deep learning-based correlative algorithms can extract more complex image features and perform better in image classification and object detection. A pixel-level defect segmentation methodology using DeepLabv3+, a classical semantic segmentation network, is proposed in this paper. Based on ResNet-18, ResNet-50 and Mobilenetv2, three DeepLabv3+ networks are constructed, which are trained and tested from data sets produced by capturing or publicizing images. The experimental results show that the performance of three DeepLabv3+ networks is close to one another on the four indicators proposed (Precision, Recall, F1-score and Accuracy), proving them to achieve defect detection and semantic segmentation, which provide new ideas and technical support for fabric defect detection.
29
Cao, Luwen, Qixin Han, Rong Luo, Li Xu, and Weikuan Jia. "Optimized YOLOv8 Model for Precise Defects Detection on Wet-Blue Hide Surface." Journal of the American Leather Chemists Association 119, no. 11 (November 1, 2024): 467–80. http://dx.doi.org/10.34314/h35hpe67.
Повний текст джерелаАнотація:
In the leather manufacturing industry, the detection of surface defects is crucial for ensuring product quality. Traditional manual inspection methods are subjective, inefficient, and susceptible to environmental influences, and can no longer meet the demands for high efficiency and quality in modern leather production. Therefore, developing a fast, accurate, and automated defect detection system has become an urgent need in the industry. Against this backdrop, this paper conducts an in-depth study and targeted optimization of the YOLOv8 algorithm, proposing a novel wet blue leather surface defect detection model, ACI-Net, to enhance detection accuracy and robustness. To address the challenge of distinguishing defects from similar background textures, this study introduces the ACMix attention module. This module effectively captures long-range dependencies in images, significantly improving the accuracy of defect recognition. The study incorporates the MetaNeXtStage module, which focuses on the effective integration of multi-scale features, enabling the model to precisely identify a wide range of defect sizes, thereby enhancing overall detection performance. Comparative experiments demonstrate that this algorithm surpasses existing models in defect detection, achieving accuracy rates of 86.2%, 99%, and 88.8% for brand, broken hole, and broken surface, respectively, thus meeting the dual requirements for precision and robustness in industrial applications.
30
Gardymova, Anna P., Mikhail N. Krakhalev, and Victor Ya Zyryanov. "Optical Textures and Orientational Structures in Cholesteric Droplets with Conical Boundary Conditions." Molecules 25, no. 7 (April 10, 2020): 1740. http://dx.doi.org/10.3390/molecules25071740.
Повний текст джерелаАнотація:
Cholesteric droplets dispersed in polymer with conical boundary conditions have been studied. The director configurations are identified by the polarising microscopy technique. The axisymmetric twisted axial-bipolar configuration with the surface circular defect at the droplet’s equator is formed at the relative chirality parameter N 0 ≤ 2.9 . The intermediate director configuration with the deformed circular defect is realised at 2.9 < N 0 < 3.95 , and the layer-like structure with the twisted surface defect loop is observed at N 0 ≥ 3.95 . The cholesteric layers in the layer-like structure are slightly distorted although the cholesteric helix is untwisted.
31
Novotná, Vladimíra, Lubor Lejček, Věra Hamplová, and Jana Vejpravová. "Defect Structures of Magnetic Nanoparticles in Smectic A Liquid Crystals." Molecules 26, no. 18 (September 21, 2021): 5717. http://dx.doi.org/10.3390/molecules26185717.
Повний текст джерелаАнотація:
Topological defects in anisotropic fluids like liquid crystals serve as a playground for the research of various effects. In this study, we concentrated on a hybrid system of chiral rod-like molecules doped by magnetic nanoparticles. In textures of the smectic A phase, we observed linear defects and found that clusters of nanoparticles promote nucleation of smectic layer defects just at the phase transition from the isotropic to the smectic A (SmA) phase. In different geometries, we studied and analysed creation of defects which can be explained by attractive elastic forces between nanoparticles in the SmA phase. On cooling the studied hybrid system, clusters grow up to the critical dimension, and the smectic texture is stabilised. The presented effects are theoretically described and explained if we consider the elastic interaction of two point defects and stabilisation of prismatic dislocation loops due to the presence of nanoparticles.
32
Xu, Haitao, Chengming Liu, Shuya Duan, Liangpin Ren, Guozhen Cheng, and Bing Hao. "A Fabric Defect Segmentation Model Based on Improved Swin-Unet with Gabor Filter." Applied Sciences 13, no. 20 (October 17, 2023): 11386. http://dx.doi.org/10.3390/app132011386.
Повний текст джерелаАнотація:
Fabric inspection is critical in fabric manufacturing. Automatic detection of fabric defects in the textile industry has always been an important research field. Previously, manual visual inspection was commonly used; however, there were drawbacks such as high labor costs, slow detection speed, and high error rates. Recently, many defect detection methods based on deep learning have been proposed. However, problems need to be solved in the existing methods, such as detection accuracy and interference of complex background textures. In this paper, we propose an efficient segmentation algorithm that combines traditional operators with deep learning networks to alleviate the existing problems. Specifically, we introduce a Gabor filter into the model, which provides the unique advantage of extracting low-level texture features to solve the problem of texture interference and enable the algorithm to converge quickly in the early stages of training. Furthermore, we design a U-shaped architecture that is not completely symmetrical, making model training easier. Meanwhile, multi-stage result fusion is proposed for precise location of defects. The design of this framework significantly improves the detection accuracy and effectively breaks through the limitations of transformer-based models. Experimental results show that on a dataset with one class, a small amount of data, and complex sample background texture, our method achieved 90.03% and 33.70% in ACC and IoU, respectively, which is almost 10% higher than other previous state of the art models. Experimental results based on three different fabric datasets consistently show that the proposed model has excellent performance and great application potential in the industrial field.
33
R, Subashini, Hemalatha R, and Muthumeenakshi K. "Dictionary Learning Based Adaptive Defect Detection In Complex Fabric Textures." International Journal of Computing and Digital Systems 14, no. 1 (September 1, 2023): 769–78. http://dx.doi.org/10.12785/ijcds/140159.
Повний текст джерела
34
Shen, Yanchun, Jinbing Wu, Jingge Wang, Saibo Wu, and Wei Hu. "Topological Defect Evolutions Guided by Varying the Initial Azimuthal Orientation." Applied Sciences 14, no. 21 (October 29, 2024): 9869. http://dx.doi.org/10.3390/app14219869.
Повний текст джерелаАнотація:
Topological defects are a key concern in numerous branches of physics. It is meaningful to exploit the topological defect evolutions during the phase transitions of condensed matter. Here, via varying the initial azimuthal orientation of the square alignment lattice in a hybrid cell, the topological defect evolution of liquid crystal during the nematic (N)–smectic A (SmA) phase transition is investigated. The director fields surrounding ±1 point defects are manipulated by predesigning the initial azimuthal orientation. When further cooled to the SmA phase, spiral toric focal conic domain (TFCD) arrays are formed as a result of twisted deformation suppression and unique symmetry breaking after the phase transition. The variation in the azimuthal orientation causes the TFCDs to degenerate from infinite rotational symmetry to quadruple rotational symmetry, thus releasing new textures for the SmA phase. Landau–de Gennes numerical modeling is adopted to reproduce the director distributions in the N phase and reveal the evolution of the topological defects. This work enriches the knowledge on the self-organization of soft matter, enhances the capability for the manipulations of topological defects, and may inspire new intriguing applications.
35
Saberironaghi, Alireza, Jing Ren, and Moustafa El-Gindy. "Defect Detection Methods for Industrial Products Using Deep Learning Techniques: A Review." Algorithms 16, no. 2 (February 8, 2023): 95. http://dx.doi.org/10.3390/a16020095.
Повний текст джерелаАнотація:
Over the last few decades, detecting surface defects has attracted significant attention as a challenging task. There are specific classes of problems that can be solved using traditional image processing techniques. However, these techniques struggle with complex textures in backgrounds, noise, and differences in lighting conditions. As a solution to this problem, deep learning has recently emerged, motivated by two main factors: accessibility to computing power and the rapid digitization of society, which enables the creation of large databases of labeled samples. This review paper aims to briefly summarize and analyze the current state of research on detecting defects using machine learning methods. First, deep learning-based detection of surface defects on industrial products is discussed from three perspectives: supervised, semi-supervised, and unsupervised. Secondly, the current research status of deep learning defect detection methods for X-ray images is discussed. Finally, we summarize the most common challenges and their potential solutions in surface defect detection, such as unbalanced sample identification, limited sample size, and real-time processing.
36
Ralló, Miquel, María S. Millán, and Jaume Escofet. "Unsupervised novelty detection using Gabor filters for defect segmentation in textures." Journal of the Optical Society of America A 26, no. 9 (August 18, 2009): 1967. http://dx.doi.org/10.1364/josaa.26.001967.
Повний текст джерела
37
Brzakovic, D., H. Beck, and N. Sufi. "An approach to defect detection in materials characterized by complex textures." Pattern Recognition 23, no. 1-2 (January 1990): 99–107. http://dx.doi.org/10.1016/0031-3203(90)90052-m.
Повний текст джерела
38
Viney, Christopher, and Wendy S. Putnam. "Characterization of sheared liquid crystalline polymers by light microscopy." Proceedings, annual meeting, Electron Microscopy Society of America 51 (August 1, 1993): 864–65. http://dx.doi.org/10.1017/s0424820100150150.
Повний текст джерелаАнотація:
It is widely observed that nematic and cholesteric liquid crystalline materials develop a one-dimensional periodic microstructure during and/or after a uniaxial draw or simple shear (Fig. 1). This property is common to lyotropic and thermotropic examples of both small-molecule and polymeric liquid crystals. The periodic microstructure gives rise to a banded texture between crossed polars (Fig 2).A material under load will extend more readily if the microstructure contains crimps that can be straightened, compared to the extension that is achieved if covalent backbone bonds are highly aligned along the direction of load. The microstructure in Fig. 1 therefore is regarded as a stiffness-reducing defect. Two classes of stiff polymer that are produced from lyotropic solutions do not exhibit banded textures: the highest modulus variant of poly(p-phenyleneterephthalamide) (Kevlar), and various natural silk fibers. However, a banded texture is present in the less stiff variants of Kevlar, and also in silk fibers that have been drawn by hand from natural secretions, which demonstrates that the defect is not intrinsic to liquid crystalline molecular order, but is related to processing.
39
Shanthalakshmi, M., Susmita mishra, V. Jananee, P. Narayana Perumal, and S. Manoj Jayakar. "Identification of Casting Product Surface Quality Using Alex net and Le-net CNN Models." Journal of Physics: Conference Series 2335, no. 1 (September 1, 2022): 012031. http://dx.doi.org/10.1088/1742-6596/2335/1/012031.
Повний текст джерелаАнотація:
Abstract Casting is a manufacturing process in which a fluid product is normally poured into a mold, which contains a hollow cavity of the preferred form, and afterwards allowed to solidify. A Casting defect is an undesirable abnormality in a metal casting procedure. There are lots of types of issues in casting like blow openings, pinholes, burr, shrinkage issues, product flaws. Defects are an undesirable thing in the casting Industry. In this job, we extracted different casting items features and then applied convolutional neural network-based models for the discovery of the casted item is great or otherwise. So, it observed that neural networks can record the colours as well as textures of casting particularly to respective, which looks like human decision-making. This design is to deploy the Django internet framework. We try out different surfaces as input to convolutional neural networks for the efficient classification of the surface defect.
40
Patil, Deepika B., Akriti Nigam, Subrajeet Mohapatra, and Sagar Nikam. "A Deep Learning Approach to Classify and Detect Defects in the Components Manufactured by Laser Directed Energy Deposition Process." Machines 11, no. 9 (August 25, 2023): 854. http://dx.doi.org/10.3390/machines11090854.
Повний текст джерелаАнотація:
This paper presents a deep learning approach to identify and classify various defects in the laser-directed energy manufactured components. It mainly focuses on the Convolutional Neural Network (CNN) architectures, such as VGG16, AlexNet, GoogLeNet and ResNet to perform the automated classification of defects. The main objectives of this research are to manufacture components using the laser-directed energy deposition process, prepare a dataset of horizontal wall structure, vertical wall structure and cuboid structure with three defective classes such as voids, flash formation, and rough textures, and one non-defective class, use this dataset with a deep learning algorithm to classify the defect and use the efficient algorithm to detect defects. The next objective is to compare the performance parameters of VGG16, AlexNet, GoogLeNet and ResNet used for classifying defects. It has been observed that the best results were obtained when the VGG16 architecture was applied to an augmented dataset. With augmentation, the VGG16 architecture gave a test accuracy of 94.7% and a precision of 80.0%. The recall value is 89.3% and an F1-Score is 89.5%. The VGG16 architecture with augmentation is highly reliable for automating the defect detection process and classifying defects in the laser additive manufactured components.
41
Mei, Shunqi, Yishan Shi, Heng Gao, and Li Tang. "Research on Fabric Defect Detection Algorithm Based on Improved YOLOv8n Algorithm." Electronics 13, no. 11 (May 21, 2024): 2009. http://dx.doi.org/10.3390/electronics13112009.
Повний текст джерелаАнотація:
In the process of fabric production, various types of defects affect the quality of a fabric. However, due to the wide variety of fabric defects, the complexity of fabric textures, and the concealment of small target defects, current fabric defect detection algorithms suffer from issues such as having a slow detection speed, low detection accuracy, and a low recognition rate of small target defects. Therefore, developing an efficient and accurate fabric defect detection system has become an urgent problem that needs to be addressed in the textile industry. Addressing the aforementioned issues, this paper proposes an improved YOLOv8n-LAW algorithm based on the YOLOv8n algorithm. First, LSKNet attention mechanisms are added to both ends of the C2f module in the backbone network to provide a broader context area, enhancing the algorithm’s feature extraction capability. Next, the PAN-FPN structure of the backbone network is replaced by the AFPN structure, so that the different levels of features of the defects are closer to the semantic information in the progressive fusion. Finally, the CIoU loss is replaced with the WIoU v3 loss, allowing the model to dynamically adjust gradient gains based on the features of fabric defects, effectively focusing on distinguishing between defective and non-defective regions. The experimental results show that the improved YOLOv8n-LAW algorithm achieved an accuracy of 97.4% and a detection speed of 46 frames per second, while effectively increasing the recognition rate of small target defects.
42
Liu, Zhoufeng, Chi Zhang, Chunlei Li, Shumin Ding, Yan Dong, and Yun Huang. "Fabric defect recognition using optimized neural networks." Journal of Engineered Fibers and Fabrics 14 (January 2019): 155892501989739. http://dx.doi.org/10.1177/1558925019897396.
Повний текст джерелаАнотація:
Fabric defect recognition is an important measure for quality control in a textile factory. This article utilizes a deep convolutional neural network to recognize defects in fabrics that have complicated textures. Although convolutional neural networks are very powerful, a large number of parameters consume considerable computation time and memory bandwidth. In real-world applications, however, the fabric defect recognition task needs to be carried out in a timely fashion on a computation-limited platform. To optimize a deep convolutional neural network, a novel method is introduced to reveal the input pattern that originally caused a specific activation in the network feature maps. Using this visualization technique, this study visualizes the features in a fully trained convolutional model and attempts to change the architecture of original neural network to reduce computational load. After a series of improvements, a new convolutional network is acquired that is more efficient to the fabric image feature extraction, and the computation load and the total number of parameters in the new network is 23% and 8.9%, respectively, of the original model. The proposed neural network is specifically tailored for fabric defect recognition in resource-constrained environments. All of the source code and pretrained models are available online at https://github.com/ZCmeteor .
43
Wu, Ying, Jian Zhou, Nicholus Tayari Akankwasa, Kai Wang, and Jun Wang. "Fabric texture representation using the stable learned discrete cosine transform dictionary." Textile Research Journal 89, no. 3 (November 28, 2017): 294–310. http://dx.doi.org/10.1177/0040517517743688.
Повний текст джерелаАнотація:
To obtain a stable fabric texture representation result and improve the computation speed, a novel method based on dictionary learning is presented. The dictionary is learned by the alternating least-squares method using discrete cosine transform (DCT) as the initiation dictionary. To test the effectiveness of the dictionary, we comprehensively investigated 42 diverse fault-free woven fabric samples, and three fabrics with defects. After the preprocessing procedure, the woven fabric samples were characterized by the learned dictionary. The experiments on 37 samples with different fabric densities demonstrated that the Peak Signal to Noise Ratio becomes larger while the Root Mean Square Error (RMSE) diminishes as the weaving density increases. For defect fabric samples, the proposed algorithm can efficiently inspect the different types of fabric flaws. Results revealed that the learned dictionary is stable, highly efficient, and suitable for modeling fabric textures. In addition, the algorithm was validated by comparing it with the K-Singular Value Decomposition dictionary and the DCT dictionary. The learned dictionary presented strikingly better results in terms of calculation speed, consistent results, and RMSE. In general, the proposed method can be applied in studying the influence of fabric density on the representation of the fabric texture and detecting fabric flaws.
44
Ben-abraham, S. I. "Development of Defect Textures in Smectic A Liquid Crystals: A Nonlinear Model." Molecular Crystals and Liquid Crystals 123, no. 1 (February 1985): 77–100. http://dx.doi.org/10.1080/00268948508074768.
Повний текст джерела
45
Tsai, Du-Ming, and Shin-Min Chao. "An anisotropic diffusion-based defect detection for sputtered surfaces with inhomogeneous textures." Image and Vision Computing 23, no. 3 (March 2005): 325–38. http://dx.doi.org/10.1016/j.imavis.2004.09.003.
Повний текст джерела
46
Li, Junfeng, and Hao Wang. "Surface defect detection of vehicle light guide plates based on an improved RetinaNet." Measurement Science and Technology 33, no. 4 (January 7, 2022): 045401. http://dx.doi.org/10.1088/1361-6501/ac4597.
Повний текст джерелаАнотація:
Abstract Aiming at the vehicle navigation light guide plate (LGP) image characteristics, such as complex and gradient textures, uneven brightness, and small defects, this paper proposes a visual inspection method for LGP defects based on an improved RetinaNet. First, we use ResNeXt50 with higher accuracy under the same parameters as the backbone network, and propose the lightweight module Ghost_module to replace the 1 × 1 convolution in the lower half of the ResNeXt_block. This can reduce the resource parameters and consumption, and speed up training and inference. Second, we propose and use an improved feature pyramid network module to improve the feature fusion network in RetinaNet. It can more effectively fuse the shallow semantic information and high-level semantic information in the backbone feature extraction network, and further improve the detection ability of small target defects. Finally, the defect detection dataset constructed based on the vehicle LGP images collected at a industrial site, and experiments are performed on the vehicle LGP dataset and Aluminum Profile Defect Identification dataset (Aluminum Profile DID). The experimental results show that the proposed method is both efficient and effective. It achieves a better average detection rate of 98.6% on the vehicle LGP dataset. The accuracy and real-time performance can meet the requirements of industrial detection.
47
Zhou, Jian, Jian Zhou, Jun Wang, and Honggang Bu. "Fabric Defect Detection Using a Hybrid and Complementary Fractal Feature Vector and FCM-based Novelty Detector." Fibres and Textiles in Eastern Europe 25 (December 31, 2017): 46–52. http://dx.doi.org/10.5604/01.3001.0010.5370.
Повний текст джерелаАнотація:
Automated detect detection in woven fabrics for quality control is still a challenging novelty detection problem. This work presents five novel fractal features based on the box-counting dimension to address the novelty detection of fabric defect. Making use of the formation of woven fabric, the fractal features are extracted in a one-dimension series obtained by projecting a fabric image along the warp and weft directions, where their complementarity in discriminating defects is taken into account. Furthermore a new novelty detector based on fuzzy c-means (FCM) is devised to deal with one-class classification of the features extracted. Finally, by jointly applying the features proposed and the FCM based novelty detector, we evaluate the method proposed for eight datasets with different defects and textures, where satisfying results are achieved with a low overall missing detection rate.
48
Zhu, Jinsong, and Jinbo Song. "An Intelligent Classification Model for Surface Defects on Cement Concrete Bridges." Applied Sciences 10, no. 3 (February 2, 2020): 972. http://dx.doi.org/10.3390/app10030972.
Повний текст джерелаАнотація:
This paper mainly improves the visual geometry group network-16 (VGG-16), which is a classic convolutional neural network (CNN), to classify the surface defects on cement concrete bridges in an accurate manner. Specifically, the number of fully connected layers was reduced by one, and the Softmax classifier was replaced with a Softmax classification layer with seven defect tags. The weight parameters of convolutional and pooling layers were shared in the pre-trained model, and the rectified linear unit (ReLU) function was taken as the activation function. The original images were collected by a road inspection vehicle driving across bridges on national and provincial highways in Jiangxi Province, China. The images on surface defects of cement concrete bridges were selected, and divided into a training set and a test set, and preprocessed through morphology-based weight adaptive denoising. To verify its performance, the improved VGG-16 was compared with traditional shallow neural networks (NNs) like the backpropagation neural network (BPNN), support vector machine (SVM), and deep CNNs like AlexNet, GoogLeNet, and ResNet on the same sample dataset of surface defects on cement concrete bridges. Judging by mean detection accuracy and top-5 accuracy, our model outperformed all the contrastive methods, and accurately differentiated between images with seven classes of defects such as normal, cracks, fracturing, plate fracturing, corner rupturing, edge/corner exfoliation, skeleton exposure, and repairs. The results indicate that our model can effectively extract the multi-layer features from surface defect images, which highlights the edges and textures. The research findings shed important new light on the detection of surface defects and classification of defect images.
49
Zhang, Yizhuo, Guanlei Wu, Shen Shi, and Huiling Yu. "WTSM-SiameseNet: A Wood-Texture-Similarity-Matching Method Based on Siamese Networks." Information 15, no. 12 (December 16, 2024): 808. https://doi.org/10.3390/info15120808.
Повний текст джерелаАнотація:
In tasks such as wood defect repair and the production of high-end wooden furniture, ensuring the consistency of the texture in repaired or jointed areas is crucial. This paper proposes the WTSM-SiameseNet model for wood-texture-similarity matching and introduces several improvements to address the issues present in traditional methods. First, to address the issue that fixed receptive fields cannot adapt to textures of different sizes, a multi-receptive field fusion feature extraction network was designed. This allows the model to autonomously select the optimal receptive field, enhancing its flexibility and accuracy when handling wood textures at different scales. Secondly, the interdependencies between layers in traditional serial attention mechanisms limit performance. To address this, a concurrent attention mechanism was designed, which reduces interlayer interference by using a dual-stream parallel structure that enhances the ability to capture features. Furthermore, to overcome the issues of existing feature fusion methods that disrupt spatial structure and lack interpretability, this study proposes a feature fusion method based on feature correlation. This approach not only preserves the spatial structure of texture features but also improves the interpretability and stability of the fused features and the model. Finally, by introducing depthwise separable convolutions, the issue of a large number of model parameters is addressed, significantly improving training efficiency while maintaining model performance. Experiments were conducted using a wood texture similarity dataset consisting of 7588 image pairs. The results show that WTSM-SiameseNet achieved an accuracy of 96.67% on the test set, representing a 12.91% improvement in accuracy and a 14.21% improvement in precision compared to the pre-improved SiameseNet. Compared to CS-SiameseNet, accuracy increased by 2.86%, and precision improved by 6.58%.
50
P. Banumathi, Et al. "DEFECTCNN: Improved Discriminative Convolution Neural Network Towards Instantaneous Automatic Detection and Classification of Complex Defect in Fabrics." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 11 (November 30, 2023): 326–35. http://dx.doi.org/10.17762/ijritcc.v11i11.9610.
Повний текст джерелаАнотація:
Due to enormous growth of textile industries has increased demand for the automatic fabric defect detection and classification system to the fabric material as it plays a crucial role in maintaining the quality of the services. Machine learning model has employed as automatic defect detection system to identify the material quality. Despite of several advantageous of the machine learning model, those models faces several challenges on handling the complex and uncertainty of varied texture and structural patterns. Further it is complex to process the boundaries and features with high degree of intra class variation and low degree of interclass variations. On leveraging and exploiting the deep learning architecture, the over lapping and varied texture patterns can be efficiently discriminated on defects. In this paper, a new deep learning architecture entitled as discriminative convolution neural model is proposed to detect and classify the defects in the fabric materials into various defect classes. Initially fabric image preprocessed on basis of the noise filtering through wiener filter and image enhancement through CLAHE technique. Enhanced image is segmented using image thresholding technique to segment it into the various regions on basis of pixel information’s by grouping the neighbouring similar pixels intensity or textures to represent a mask. Segmented image regions are projected to the convolution neural network. Convolution layer of network is to extract the features from its composition containing kernels with different weights. It computes the high level features for different pixels based on surrounding and neighbouring pixel values on striding to produce the feature map containing gradient and edge of the images. ReLU activation function is applied to reduce the non linearity among the features in the feature map. Pooling layer of the model down-sample the convolved features to produce the activation map. Activation map is obtained using max pooling as it returns maximum value from the segment of the image processed using kernels. Activation map is transformed into tabular structure to perform the classification easily. In addition drop out layer is incorporated in the model to eliminate the overfitting issue during classification on reducing the correlation among the neurons. Fully connected layers of the model is used to learn the flattened features with weights and bias to classify the flatten features using softmax layer on basis of defect classes such as Hole , Color Spot, Thread Error and foreign body. Experimental analysis of the proposed architecture is carried out on TILDA dataset using cross fold validation to analyse the representation ability to discriminate the features with large variance between the different classes. From the results, it is confirming that proposed architecture exhibiting higher performance in classification accuracy of 98.43% in classifying the fabric defect on compared with conventional approaches